Tag
This review paper surveys the application of large models in battery prognostics and health management, addressing long-standing challenges and proposing a roadmap for future research in this domain.
This paper introduces FlowBD-E1, an early-cycle generative forecasting framework that predicts full charge voltage/current trajectories for iron-chromium flow batteries, enabling accurate health management with sub-percent error rates in industrial validation.
A systematic literature review of 212 studies investigates how Physics-Informed Machine Learning (PIML) is applied in Prognostics and Health Management (PHM), introducing a four-class classification scheme and finding that PIML consistently improves predictive performance over conventional baselines, though the literature is skewed toward batteries and bearings and lacks strong evidence for claims regarding generalization and interpretability.
This paper proposes a framework for applying tabular foundation models to industrial time series for prognostics and health management, demonstrating strong performance and data efficiency across multiple PHM tasks.
This paper benchmarks five uncertainty quantification methods for neural network predictions of turbine gas temperature, evaluating trade-offs in coverage, width, and stability to guide prognostics and health management in engines.